| Raman spectroscopy has the potential to significantly aid in the research, diagnosis and treatment of cancer. The information dense, complex spectra generate vast datasets in which subtle correlations among peaks often provide essential clues for biological analysis and interpretation. Thus, the implementation of advanced data mining techniques is imperative for complete, rapid and accurate data analysis of large spectral datasets; particularly in regards to clinical translation of the technology. Standard classification models have shown to perform poorly on such high dimensional datasets, typically transforming the original feature space, and making it unfeasible to ascribe biological relevance to the discriminating features. In the first part of this work, Raman spectroscopy is combined with a novel data mining framework, known as Fisher-based Feature Selection-Support Vector Machines (FFS-SVM), to classify and characterize, in-situ, five breast cell lines based on differences in biochemical composition (e.g. lipids, DNA, protein, carbohydrates). This provides both high classification accuracy of cell type, as well as extraction of biologically relevant 'biomarker-type' information based on selected features from each classification 17 schema. The subsequent phase of this work is based on further broadening the application of this Raman spectroscopic-based platform for developing a non-invasive, real-time, in-vitro assay methodology for the classification and characterization of the effects and efficacy of anti-cancer agents on breast cancer cells. Assessment of efficacy by classification of cell spectra as apoptotic, dead/necrotic, or healthy is achieved. Correlation of the features, or spectral peaks, to the corresponding biology reveals that the Raman-based platform provides a wealth information comparable to that provided by several of the most commonly used conventional assay methods, yet in a more efficient, effective, and non-invasive manner. The extension of FFS-SVM to a multiclass classification framework, along with an optimized cluster analysis, provides classification accuracies of greater than 95%, as well as biologically relevant spectral features associated with the agent's mechanism of action (MOA). Continued development of this platform could improve pre-clinical model predictive capabilities, while concurrently providing insight into the MOA of potential anti-cancer agents, thus increasing drug development and screening efficiency, while decreasing developmental cost. |
